Equivariant Graph Neural Networks for 3D Macromolecular Structure
arXiv:2106.03843
Abstract
Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on three out of eight tasks in the ATOM3D benchmark, is tied for first on two others, and is competitive with equivariant networks using higher-order representations and spherical harmonic convolutions. In addition, we demonstrate that transfer learning can further improve performance on certain downstream tasks. Code is available at https://github.com/drorlab/gvp-pytorch.
arXiv commentWCB @ ICML 2021 + link to code
References in corpus (7)
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Equivariant message passing for the prediction of tensorial properties and molecular spectra
- Cormorant: Covariant Molecular Neural Networks
- E(n) Equivariant Graph Neural Networks
- N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
- Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
- Protein model quality assessment using rotation-equivariant, hierarchical neural networks